Comments (13)
Hi, thanks for catching this! I added dummy to the fetching script.
from interactive-deep-colorization.
No problem. I'm actually still unable to run this notebook due to
W0515 03:20:31.042323 3789 _caffe.cpp:142] Net('./models/global_model/global_stats.prototxt', 1, weights='./models/global_model/dummy.caffemodel')
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format caffe.NetParameter: 99:16: Message type "caffe.LayerParameter" has no field named "resize_param".
Maybe I have something wrong with caffe or protobuf installation, but ideepcolor.py and DemoInteractiveColorization.ipynb work great.
from interactive-deep-colorization.
Great, thanks for trying our code!
I slightly changed global_stats.prototxt to use pooling instead of resize. Does it work now?
from interactive-deep-colorization.
Almost. It looks like a little inconsistency in filenames.
caffe_files/caffe_traininglayers.py:import rz_fcns_nohdf5 as rz
caffe_files/caffe_datalayers.py:import rz_fcns as rz
caffe_files/color_quantization.py:import rz_fcns as rz
but there is only ./caffe_files/rz_fcns_nohdf5.py
I changed all names to rz_fcns and it looks like the problem is fixed. At least another notebook and ideepcolor.py work correctly. Now I get
IOError: [Errno 2] No such file or directory: '/home/eecs/rich.zhang/src/projects/cross_domain/save/ab_grid_10/pts_in_hull.npy'
from interactive-deep-colorization.
from interactive-deep-colorization.
cant donload this programm.... Can you give please link for me?
from interactive-deep-colorization.
Thanks @Tranvick. I changed the import and the pathing to the reference grid files. Let me know if it works now.
from interactive-deep-colorization.
Have you full version whith ,exe file?
from interactive-deep-colorization.
@Antoha-94 эта программа не для винды. Если хочешь, бери исходники и доделывай. Но не мешай тут. Тут другая тема.
from interactive-deep-colorization.
No, it does not work. I still get
IOError: [Errno 2] No such file or directory: '/home/eecs/rich.zhang/src/projects/cross_domain/save/ab_grid_10/pts_in_hull.npy'
This is because you have several places where you refer to files in /home/eecs/rich.zhang/... like
caffe_files/caffe_traininglayers.py: self.ENC_DIR = '/home/eecs/rich.zhang/src/projects/cross_domain/save/ab_grid_10' caffe_files/caffe_datalayers.py: self.ENC_DIR = '/home/eecs/rich.zhang/src/projects/cross_domain/save/ab_grid_10' caffe_files/caffe_datalayers.py: def __init__(self,alpha,gamma=0,verbose=True,priorFile='/home/eecs/rich.zhang/src/projects/cross_domain/save/ab_grid_10/prior_probs.npy',genc=-1): caffe_files/caffe_datalayers.py: self.nnenc = cq.NNEncode(self.NN,self.sigma,km_filepath='/home/eecs/rich.zhang/src/projects/cross_domain/save/ab_grid_10/pts_in_hull.npy') caffe_files/rz_fcns_nohdf5.py: dummyMeanFile = '/home/eecs/rich.zhang/src/libs/caffe5/python/caffe/imagenet/ilsvrc_2012_mean.npy' caffe_files/rz_fcns_nohdf5.py: dummyMeanFile = '/home/eecs/rich.zhang/data_rzhang/models/caffe/placesCNN_upgraded/places_mean.mat' caffe_files/color_quantization.py: def __init__(self,NN,sigma,km_filepath='/home/eecs/rich.zhang/data_rzhang/models/caffe/cross_domain/l_to_ab/2015_02_12_classification_nn_rbf/cc_k150.
The other programs work correctly.
from interactive-deep-colorization.
I fixed this issue by changing caffe_files/caffe_datalayers.py:42 from
self.ENC_DIR = '/home/eecs/rich.zhang/src/projects/cross_domain/save/ab_grid_10
to
self.ENC_DIR = 'data/color_bins'
But it will only work if you run notebook from interactive-deep-colorization/ folder
Now I get this
from interactive-deep-colorization.
I'm not sure but It could be scikit-learn related problem. Which version of scikit-learn do you use? I have 0.18.1
from interactive-deep-colorization.
Fixed this by typecasting NN as an int. https://github.com/junyanz/interactive-deep-colorization/blob/master/caffe_files/color_quantization.py#L19
. An older version of scikit-learn may have been typecasting automatically. Thanks!
from interactive-deep-colorization.
Related Issues (20)
- Local hints render area too small HOT 4
- gpu [GPU_ID]??? Interactive Deep Colorization windows 10 64-bit HOT 12
- OSError Preventing Deepcolor Function? HOT 7
- img_pred = cid.net_forward(input_ab,input_mask) Colab crashes while prediction in Global Demo file HOT 2
- SystemError: <Boost.Python.function object at 0x17369c0> returned NULL without setting an error HOT 1
- Trouble installing PyQt4 on windows 10 using Anaconda HOT 1
- Retain the Original Colors
- Windows 7 GUI not starting HOT 2
- RuntimeError: Error(s) in loading state_dict for SIGGRAPHGenerator
- Wrong color value in put_point function
- Just a note if pip install pytorch torchvision doesn't work
- error: "name 'unicode' is not defined" HOT 1
- On Windows 10 with pytorch, it will only use the CPU despite saying it's using the GPU HOT 1
- Failed to load module "appmenu-gtk-module" HOT 1
- What is a,b value for black color. HOT 3
- The QT5 version expects qt4 libraries. it is impossible for a lay person like me to get QT4 on Modern Linux distros HOT 2
- can you make it even harder to setup enviroment ?
- Question about training and demo
- Question about the paper
- Model URL no longer working HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from interactive-deep-colorization.